scrna-cell-type-annotator

Auto-annotate cell clusters from single-cell RNA data using marker genes.

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/scrna-cell-type-annotator/SKILL.md

Quality

Content

42%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill ships a real, runnable script and a sensible workflow, but the SKILL.md body is padded with generic template sections, never demonstrates an actual annotation run, and lacks output-validation for a batch operation.

Suggestions

Remove or condense generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) and deduplicate the repeated py_compile/--help commands to one verification section.

Show a concrete end-to-end command using the script's real flags (e.g., `python scripts/main.py --demo` or `--markers clusters.csv`) and reconcile the Parameters list with the script's actual arguments.

Add an output-validation checkpoint to the workflow (e.g., inspect the predicted cell types and confidence scores, re-run with adjusted markers if a cluster is unresolved) to satisfy the batch-operation feedback-loop expectation.

Dimension	Reasoning	Score
Conciseness	The body carries sizable generic template boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that Claude already knows and that is not specific to scRNA, and repeats `python -m py_compile scripts/main.py` / `python scripts/main.py --help` across three sections, fitting 'noticeably verbose; several unnecessary padded sections'.	2 / 5
Actionability	A real executable script exists and concrete commands are given, but the body never shows the actual annotation command (only --help and py_compile), and the Parameters list (tissue_type, species) does not match the script's actual flags, so guidance is concrete but incomplete.	3 / 5
Workflow Clarity	A sequenced Workflow and a pre-run py_compile checkpoint exist, but annotating all clusters is a batch operation with no output-validation feedback loop, so per the rubric cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Sections are clearly organized and reference the real one-level-deep scripts/main.py, but the bulk of material is inlined in a 190-line SKILL.md with no separated reference files, and requirements.txt is referenced but absent, fitting 'some structure; references present but content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear, specific purpose and niche but stops at a single action and omits any 'when to use' trigger guidance, which caps completeness and limits trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when annotating scRNA-seq clusters, identifying cell types from marker genes, or the user mentions single-cell RNA-seq, .h5ad files, or cluster labels').

Include common synonyms and extensions such as 'scRNA', 'scRNA-seq', and '.h5ad' to broaden natural trigger coverage.

List one or two more concrete actions (e.g., 'score and rank candidate cell types, report confidence levels') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('single-cell RNA data') and one concrete action ('Auto-annotate cell clusters') with its mechanism ('using marker genes'), but lists only a single action rather than several, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Has a clear 'what' (auto-annotate cell clusters via marker genes) but no 'Use when...' or equivalent trigger clause, so per the rubric guidance completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes relevant natural terms ('cell clusters', 'single-cell RNA data', 'marker genes') but omits the very common synonym 'scRNA'/'scRNA-seq' and any file extensions, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (scRNA cell-type annotation) that is mostly distinct, with only minor overlap risk against closely related scRNA skills (clustering, differential expression); fits 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/scrna-cell-type-annotator/SKILL.md
Commit: f5ef65b

Reviewed: ~7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.